ts-best-practices

Pass

Audited by Gen Agent Trust Hub on May 13, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted user-provided TypeScript code.
  • Ingestion points: Code snippets or files provided for review and refactoring, such as those triggered by the "audit this ts file" command.
  • Boundary markers: Absent. The skill does not instruct the agent to use delimiters or ignore embedded instructions within the code being analyzed.
  • Capability inventory: The agent's file system access and code modification capabilities.
  • Sanitization: Absent. There are no instructions to escape or validate the contents of the processed code files.
  • [EXTERNAL_DOWNLOADS]: Mentions well-known technology libraries type-fest and ts-pattern as references for utility types and exhaustive matching.
Audit Metadata
Risk Level
SAFE
Analyzed
May 13, 2026, 10:43 PM